ultralytics 8.3.77__py3-none-any.whl → 8.3.79__py3-none-any.whl

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.77"
+__version__ = "8.3.79"
 
 import os
 

ultralytics/cfg/models/12/yolo12-cls.yaml

@@ -0,0 +1,32 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-cls image classification model
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/classify
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n-cls.yaml' will call yolo12-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 152 layers, 1,820,976 parameters, 1,820,976 gradients, 3.7 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 152 layers, 6,206,992 parameters, 6,206,992 gradients, 13.6 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 172 layers, 12,083,088 parameters, 12,083,088 gradients, 44.2 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 312 layers, 15,558,640 parameters, 15,558,640 gradients, 56.9 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 312 layers, 34,172,592 parameters, 34,172,592 gradients, 126.5 GFLOPs
+
+# YOLO12n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, Classify, [nc]] # Classify

ultralytics/cfg/models/12/yolo12-obb.yaml

@@ -0,0 +1,48 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/obb
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n-obb.yaml' will call yolo12-obb.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 287 layers, 2,673,955 parameters, 2,673,939 gradients, 6.9 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 287 layers, 9,570,275 parameters, 9,570,259 gradients, 22.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 307 layers, 21,048,003 parameters, 21,047,987 gradients, 71.8 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 503 layers, 27,299,619 parameters, 27,299,603 gradients, 93.4 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 503 layers, 61,119,939 parameters, 61,119,923 gradients, 208.6 GFLOPs
+
+# YOLO12n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, OBB, [nc, 1]] # Detect(P3, P4, P5)

ultralytics/cfg/models/12/yolo12-pose.yaml

@@ -0,0 +1,49 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/pose
+
+# Parameters
+nc: 80 # number of classes
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+scales: # model compound scaling constants, i.e. 'model=yolo12n-pose.yaml' will call yolo12-pose.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 287 layers, 2,886,715 parameters, 2,886,699 gradients, 7.8 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 287 layers, 9,774,155 parameters, 9,774,139 gradients, 23.5 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 307 layers, 21,057,753 parameters, 21,057,737 gradients, 71.8 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 503 layers, 27,309,369 parameters, 27,309,353 gradients, 93.5 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 503 layers, 61,134,489 parameters, 61,134,473 gradients, 208.7 GFLOPs
+
+# YOLO12n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, Pose, [nc, kpt_shape]] # Detect(P3, P4, P5)

ultralytics/cfg/models/12/yolo12-seg.yaml

@@ -0,0 +1,48 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-seg instance segmentation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/segment
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n-seg.yaml' will call yolo12-seg.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 294 layers, 2,855,056 parameters, 2,855,040 gradients, 10.6 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 294 layers, 9,938,592 parameters, 9,938,576 gradients, 35.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 314 layers, 22,505,376 parameters, 22,505,360 gradients, 123.5 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 510 layers, 28,756,992 parameters, 28,756,976 gradients, 145.1 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 510 layers, 64,387,264 parameters, 64,387,248 gradients, 324.6 GFLOPs
+
+# YOLO12n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

ultralytics/cfg/models/12/yolo12.yaml

@@ -0,0 +1,48 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12 object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n.yaml' will call yolo12.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 272 layers, 2,602,288 parameters, 2,602,272 gradients, 6.7 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 272 layers, 9,284,096 parameters, 9,284,080 gradients, 21.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 292 layers, 20,199,168 parameters, 20,199,152 gradients, 68.1 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 488 layers, 26,450,784 parameters, 26,450,768 gradients, 89.7 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 488 layers, 59,210,784 parameters, 59,210,768 gradients, 200.3 GFLOPs
+
+# YOLO12n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/data/annotator.py

@@ -58,15 +58,13 @@ def auto_annotate(
 
     for result in det_results:
         class_ids = result.boxes.cls.int().tolist()  # noqa
-        if len(class_ids):
+        if class_ids:
             boxes = result.boxes.xyxy  # Boxes object for bbox outputs
             sam_results = sam_model(result.orig_img, bboxes=boxes, verbose=False, save=False, device=device)
             segments = sam_results[0].masks.xyn  # noqa
 
             with open(f"{Path(output_dir) / Path(result.path).stem}.txt", "w") as f:
-                for i in range(len(segments)):
-                    s = segments[i]
-                    if len(s) == 0:
-                        continue
-                    segment = map(str, segments[i].reshape(-1).tolist())
-                    f.write(f"{class_ids[i]} " + " ".join(segment) + "\n")
+                for i, s in enumerate(segments):
+                    if s.any():
+                        segment = map(str, s.reshape(-1).tolist())
+                        f.write(f"{class_ids[i]} " + " ".join(segment) + "\n")

ultralytics/data/augment.py

@@ -1364,17 +1364,26 @@ class RandomHSV:
             >>> hsv_augmenter(labels)
             >>> augmented_img = labels["img"]
         """
-        img = labels["img"]
         if self.hgain or self.sgain or self.vgain:
-            r = np.random.uniform(-1, 1, 3) * [self.hgain, self.sgain, self.vgain] + 1  # random gains
-            hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
+            img = labels["img"]
             dtype = img.dtype  # uint8
 
+            # Original implementation (bug) from ultralytics<=8.3.78
+            # r = np.random.uniform(-1, 1, 3) * [self.hgain, self.sgain, self.vgain] + 1  # random gains
+            # x = np.arange(0, 256, dtype=r.dtype)
+            # lut_hue = ((x * r[0]) % 180).astype(dtype)
+            # lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
+            # lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
+
+            # Fixed implementation in https://github.com/ultralytics/ultralytics/pull/19311
+            r = np.random.uniform(-1, 1, 3) * (self.hgain, self.sgain, self.vgain) * (180, 255, 255)  # random gains
             x = np.arange(0, 256, dtype=r.dtype)
-            lut_hue = ((x * r[0]) % 180).astype(dtype)
-            lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
-            lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
+            lut_hue = ((x + r[0]) % 180).astype(dtype)
+            lut_sat = np.clip(x + r[1], 0, 255).astype(dtype)
+            lut_val = np.clip(x + r[2], 0, 255).astype(dtype)
+            lut_sat[0] = 0  # prevent pure white changing color
 
+            hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
             im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
             cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=img)  # no return needed
         return labels
@@ -1484,7 +1493,7 @@ class LetterBox:
     Attributes:
         new_shape (tuple): Target shape (height, width) for resizing.
         auto (bool): Whether to use minimum rectangle.
-        scaleFill (bool): Whether to stretch the image to new_shape.
+        scale_fill (bool): Whether to stretch the image to new_shape.
         scaleup (bool): Whether to allow scaling up. If False, only scale down.
         stride (int): Stride for rounding padding.
         center (bool): Whether to center the image or align to top-left.
@@ -1499,7 +1508,7 @@ class LetterBox:
         >>> updated_instances = result["instances"]
     """
 
-    def __init__(self, new_shape=(640, 640), auto=False, scaleFill=False, scaleup=True, center=True, stride=32):
+    def __init__(self, new_shape=(640, 640), auto=False, scale_fill=False, scaleup=True, center=True, stride=32):
         """
         Initialize LetterBox object for resizing and padding images.
 
@@ -1509,7 +1518,7 @@ class LetterBox:
         Args:
             new_shape (Tuple[int, int]): Target size (height, width) for the resized image.
             auto (bool): If True, use minimum rectangle to resize. If False, use new_shape directly.
-            scaleFill (bool): If True, stretch the image to new_shape without padding.
+            scale_fill (bool): If True, stretch the image to new_shape without padding.
             scaleup (bool): If True, allow scaling up. If False, only scale down.
             center (bool): If True, center the placed image. If False, place image in top-left corner.
             stride (int): Stride of the model (e.g., 32 for YOLOv5).
@@ -1517,17 +1526,17 @@ class LetterBox:
         Attributes:
             new_shape (Tuple[int, int]): Target size for the resized image.
             auto (bool): Flag for using minimum rectangle resizing.
-            scaleFill (bool): Flag for stretching image without padding.
+            scale_fill (bool): Flag for stretching image without padding.
             scaleup (bool): Flag for allowing upscaling.
             stride (int): Stride value for ensuring image size is divisible by stride.
 
         Examples:
-            >>> letterbox = LetterBox(new_shape=(640, 640), auto=False, scaleFill=False, scaleup=True, stride=32)
+            >>> letterbox = LetterBox(new_shape=(640, 640), auto=False, scale_fill=False, scaleup=True, stride=32)
             >>> resized_img = letterbox(original_img)
         """
         self.new_shape = new_shape
         self.auto = auto
-        self.scaleFill = scaleFill
+        self.scale_fill = scale_fill
         self.scaleup = scaleup
         self.stride = stride
         self.center = center  # Put the image in the middle or top-left
@@ -1573,7 +1582,7 @@ class LetterBox:
         dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
         if self.auto:  # minimum rectangle
             dw, dh = np.mod(dw, self.stride), np.mod(dh, self.stride)  # wh padding
-        elif self.scaleFill:  # stretch
+        elif self.scale_fill:  # stretch
             dw, dh = 0.0, 0.0
             new_unpad = (new_shape[1], new_shape[0])
             ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios

ultralytics/data/converter.py

@@ -274,13 +274,13 @@ def convert_coco(
         # Create image dict
         images = {f"{x['id']:d}": x for x in data["images"]}
         # Create image-annotations dict
-        imgToAnns = defaultdict(list)
+        annotations = defaultdict(list)
         for ann in data["annotations"]:
-            imgToAnns[ann["image_id"]].append(ann)
+            annotations[ann["image_id"]].append(ann)
 
         image_txt = []
         # Write labels file
-        for img_id, anns in TQDM(imgToAnns.items(), desc=f"Annotations {json_file}"):
+        for img_id, anns in TQDM(annotations.items(), desc=f"Annotations {json_file}"):
             img = images[f"{img_id:d}"]
             h, w = img["height"], img["width"]
             f = str(Path(img["coco_url"]).relative_to("http://images.cocodataset.org")) if lvis else img["file_name"]

ultralytics/engine/exporter.py

@@ -170,6 +170,7 @@ def try_export(inner_func):
     def outer_func(*args, **kwargs):
         """Export a model."""
         prefix = inner_args["prefix"]
+        dt = 0.0
         try:
             with Profile() as dt:
                 f, model = inner_func(*args, **kwargs)
@@ -309,9 +310,8 @@ class Exporter:
                 "WARNING ⚠️ INT8 export requires a missing 'data' arg for calibration. "
                 f"Using default 'data={self.args.data}'."
             )
-        if tfjs:
-            if ARM64 and LINUX:
-                raise SystemError("TensorFlow.js export not supported on ARM64 Linux")
+        if tfjs and (ARM64 and LINUX):
+            raise SystemError("TensorFlow.js export not supported on ARM64 Linux")
 
         # Input
         im = torch.zeros(self.args.batch, 3, *self.imgsz).to(self.device)
@@ -419,7 +419,7 @@ class Exporter:
             if pb or tfjs:  # pb prerequisite to tfjs
                 f[6], _ = self.export_pb(keras_model=keras_model)
             if tflite:
-                f[7], _ = self.export_tflite(keras_model=keras_model, nms=False, agnostic_nms=self.args.agnostic_nms)
+                f[7], _ = self.export_tflite()
             if edgetpu:
                 f[8], _ = self.export_edgetpu(tflite_model=Path(f[5]) / f"{self.file.stem}_full_integer_quant.tflite")
             if tfjs:
@@ -1077,7 +1077,7 @@ class Exporter:
         return f, None
 
     @try_export
-    def export_tflite(self, keras_model, nms, agnostic_nms, prefix=colorstr("TensorFlow Lite:")):
+    def export_tflite(self, prefix=colorstr("TensorFlow Lite:")):
         """YOLO TensorFlow Lite export."""
         # BUG https://github.com/ultralytics/ultralytics/issues/13436
         import tensorflow as tf  # noqa

ultralytics/engine/trainer.py

@@ -567,6 +567,10 @@ class BaseTrainer:
         except Exception as e:
             raise RuntimeError(emojis(f"Dataset '{clean_url(self.args.data)}' error ❌ {e}")) from e
         self.data = data
+        if self.args.single_cls:
+            LOGGER.info("Overriding class names with single class.")
+            self.data["names"] = {0: "item"}
+            self.data["nc"] = 1
         return data["train"], data.get("val") or data.get("test")
 
     def setup_model(self):

ultralytics/models/rtdetr/predict.py

@@ -72,7 +72,7 @@ class RTDETRPredictor(BasePredictor):
     def pre_transform(self, im):
         """
         Pre-transforms the input images before feeding them into the model for inference. The input images are
-        letterboxed to ensure a square aspect ratio and scale-filled. The size must be square(640) and scaleFilled.
+        letterboxed to ensure a square aspect ratio and scale-filled. The size must be square(640) and scale_filled.
 
         Args:
             im (list[np.ndarray] |torch.Tensor): Input images of shape (N,3,h,w) for tensor, [(h,w,3) x N] for list.
@@ -80,5 +80,5 @@ class RTDETRPredictor(BasePredictor):
         Returns:
             (list): List of pre-transformed images ready for model inference.
         """
-        letterbox = LetterBox(self.imgsz, auto=False, scaleFill=True)
+        letterbox = LetterBox(self.imgsz, auto=False, scale_fill=True)
         return [letterbox(image=x) for x in im]

ultralytics/models/rtdetr/val.py

@@ -34,7 +34,7 @@ class RTDETRDataset(YOLODataset):
             hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
             transforms = v8_transforms(self, self.imgsz, hyp, stretch=True)
         else:
-            # transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), auto=False, scaleFill=True)])
+            # transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), auto=False, scale_fill=True)])
             transforms = Compose([])
         transforms.append(
             Format(

ultralytics/models/yolo/detect/val.py

@@ -186,7 +186,7 @@ class DetectionValidator(BaseValidator):
         self.nt_per_class = np.bincount(stats["target_cls"].astype(int), minlength=self.nc)
         self.nt_per_image = np.bincount(stats["target_img"].astype(int), minlength=self.nc)
         stats.pop("target_img", None)
-        if len(stats) and stats["tp"].any():
+        if len(stats):
             self.metrics.process(**stats)
         return self.metrics.results_dict
 

ultralytics/nn/autobackend.py

@@ -197,12 +197,13 @@ class AutoBackend(nn.Module):
             import onnxruntime
 
             providers = ["CPUExecutionProvider"]
-            if cuda and "CUDAExecutionProvider" in onnxruntime.get_available_providers():
-                providers.insert(0, "CUDAExecutionProvider")
-            elif cuda:  # Only log warning if CUDA was requested but unavailable
-                LOGGER.warning("WARNING ⚠️ Failed to start ONNX Runtime with CUDA. Using CPU...")
-                device = torch.device("cpu")
-                cuda = False
+            if cuda:
+                if "CUDAExecutionProvider" in onnxruntime.get_available_providers():
+                    providers.insert(0, "CUDAExecutionProvider")
+                else:  # Only log warning if CUDA was requested but unavailable
+                    LOGGER.warning("WARNING ⚠️ Failed to start ONNX Runtime with CUDA. Using CPU...")
+                    device = torch.device("cpu")
+                    cuda = False
             LOGGER.info(f"Using ONNX Runtime {providers[0]}")
             if onnx:
                 session = onnxruntime.InferenceSession(w, providers=providers)
@@ -223,7 +224,7 @@ class AutoBackend(nn.Module):
             output_names = [x.name for x in session.get_outputs()]
             metadata = session.get_modelmeta().custom_metadata_map
             dynamic = isinstance(session.get_outputs()[0].shape[0], str)
-            fp16 = True if "float16" in session.get_inputs()[0].type else False
+            fp16 = "float16" in session.get_inputs()[0].type
             if not dynamic:
                 io = session.io_binding()
                 bindings = []

ultralytics/nn/modules/__init__.py

@@ -30,6 +30,7 @@ from .block import (
     SPP,
     SPPELAN,
     SPPF,
+    A2C2f,
     AConv,
     ADown,
     Attention,
@@ -160,4 +161,5 @@ __all__ = (
     "PSA",
     "TorchVision",
     "Index",
+    "A2C2f",
 )

ultralytics/nn/modules/block.py

@@ -1154,3 +1154,205 @@ class TorchVision(nn.Module):
         else:
             y = self.m(x)
         return y
+
+
+class AAttn(nn.Module):
+    """
+    Area-attention module for YOLO models, providing efficient attention mechanisms.
+
+    This module implements an area-based attention mechanism that processes input features in a spatially-aware manner,
+    making it particularly effective for object detection tasks.
+
+    Attributes:
+        area (int): Number of areas the feature map is divided.
+        num_heads (int): Number of heads into which the attention mechanism is divided.
+        head_dim (int): Dimension of each attention head.
+        qkv (Conv): Convolution layer for computing query, key and value tensors.
+        proj (Conv): Projection convolution layer.
+        pe (Conv): Position encoding convolution layer.
+
+    Methods:
+        forward: Applies area-attention to input tensor.
+
+    Examples:
+        >>> attn = AAttn(dim=256, num_heads=8, area=4)
+        >>> x = torch.randn(1, 256, 32, 32)
+        >>> output = attn(x)
+        >>> print(output.shape)
+        torch.Size([1, 256, 32, 32])
+    """
+
+    def __init__(self, dim, num_heads, area=1):
+        """
+        Initializes an Area-attention module for YOLO models.
+
+        Args:
+            dim (int): Number of hidden channels.
+            num_heads (int): Number of heads into which the attention mechanism is divided.
+            area (int): Number of areas the feature map is divided, default is 1.
+        """
+        super().__init__()
+        self.area = area
+
+        self.num_heads = num_heads
+        self.head_dim = head_dim = dim // num_heads
+        all_head_dim = head_dim * self.num_heads
+
+        self.qkv = Conv(dim, all_head_dim * 3, 1, act=False)
+        self.proj = Conv(all_head_dim, dim, 1, act=False)
+        self.pe = Conv(all_head_dim, dim, 7, 1, 3, g=dim, act=False)
+
+    def forward(self, x):
+        """Processes the input tensor 'x' through the area-attention."""
+        B, C, H, W = x.shape
+        N = H * W
+
+        qkv = self.qkv(x).flatten(2).transpose(1, 2)
+        if self.area > 1:
+            qkv = qkv.reshape(B * self.area, N // self.area, C * 3)
+            B, N, _ = qkv.shape
+        q, k, v = (
+            qkv.view(B, N, self.num_heads, self.head_dim * 3)
+            .permute(0, 2, 3, 1)
+            .split([self.head_dim, self.head_dim, self.head_dim], dim=2)
+        )
+        attn = (q.transpose(-2, -1) @ k) * (self.head_dim**-0.5)
+        attn = attn.softmax(dim=-1)
+        x = v @ attn.transpose(-2, -1)
+        x = x.permute(0, 3, 1, 2)
+        v = v.permute(0, 3, 1, 2)
+
+        if self.area > 1:
+            x = x.reshape(B // self.area, N * self.area, C)
+            v = v.reshape(B // self.area, N * self.area, C)
+            B, N, _ = x.shape
+
+        x = x.reshape(B, H, W, C).permute(0, 3, 1, 2).contiguous()
+        v = v.reshape(B, H, W, C).permute(0, 3, 1, 2).contiguous()
+
+        x = x + self.pe(v)
+        return self.proj(x)
+
+
+class ABlock(nn.Module):
+    """
+    Area-attention block module for efficient feature extraction in YOLO models.
+
+    This module implements an area-attention mechanism combined with a feed-forward network for processing feature maps.
+    It uses a novel area-based attention approach that is more efficient than traditional self-attention while
+    maintaining effectiveness.
+
+    Attributes:
+        attn (AAttn): Area-attention module for processing spatial features.
+        mlp (nn.Sequential): Multi-layer perceptron for feature transformation.
+
+    Methods:
+        _init_weights: Initializes module weights using truncated normal distribution.
+        forward: Applies area-attention and feed-forward processing to input tensor.
+
+    Examples:
+        >>> block = ABlock(dim=256, num_heads=8, mlp_ratio=1.2, area=1)
+        >>> x = torch.randn(1, 256, 32, 32)
+        >>> output = block(x)
+        >>> print(output.shape)
+        torch.Size([1, 256, 32, 32])
+    """
+
+    def __init__(self, dim, num_heads, mlp_ratio=1.2, area=1):
+        """
+        Initializes an Area-attention block module for efficient feature extraction in YOLO models.
+
+        This module implements an area-attention mechanism combined with a feed-forward network for processing feature
+        maps. It uses a novel area-based attention approach that is more efficient than traditional self-attention
+        while maintaining effectiveness.
+
+        Args:
+            dim (int): Number of input channels.
+            num_heads (int): Number of heads into which the attention mechanism is divided.
+            mlp_ratio (float): Expansion ratio for MLP hidden dimension.
+            area (int): Number of areas the feature map is divided.
+        """
+        super().__init__()
+
+        self.attn = AAttn(dim, num_heads=num_heads, area=area)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = nn.Sequential(Conv(dim, mlp_hidden_dim, 1), Conv(mlp_hidden_dim, dim, 1, act=False))
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        """Initialize weights using a truncated normal distribution."""
+        if isinstance(m, nn.Conv2d):
+            nn.init.trunc_normal_(m.weight, std=0.02)
+            if m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+
+    def forward(self, x):
+        """Forward pass through ABlock, applying area-attention and feed-forward layers to the input tensor."""
+        x = x + self.attn(x)
+        return x + self.mlp(x)
+
+
+class A2C2f(nn.Module):
+    """
+    Area-Attention C2f module for enhanced feature extraction with area-based attention mechanisms.
+
+    This module extends the C2f architecture by incorporating area-attention and ABlock layers for improved feature
+    processing. It supports both area-attention and standard convolution modes.
+
+    Attributes:
+        cv1 (Conv): Initial 1x1 convolution layer that reduces input channels to hidden channels.
+        cv2 (Conv): Final 1x1 convolution layer that processes concatenated features.
+        gamma (nn.Parameter | None): Learnable parameter for residual scaling when using area attention.
+        m (nn.ModuleList): List of either ABlock or C3k modules for feature processing.
+
+    Methods:
+        forward: Processes input through area-attention or standard convolution pathway.
+
+    Examples:
+        >>> m = A2C2f(512, 512, n=1, a2=True, area=1)
+        >>> x = torch.randn(1, 512, 32, 32)
+        >>> output = m(x)
+        >>> print(output.shape)
+        torch.Size([1, 512, 32, 32])
+    """
+
+    def __init__(self, c1, c2, n=1, a2=True, area=1, residual=False, mlp_ratio=2.0, e=0.5, g=1, shortcut=True):
+        """
+        Area-Attention C2f module for enhanced feature extraction with area-based attention mechanisms.
+
+        Args:
+            c1 (int): Number of input channels.
+            c2 (int): Number of output channels.
+            n (int): Number of ABlock or C3k modules to stack.
+            a2 (bool): Whether to use area attention blocks. If False, uses C3k blocks instead.
+            area (int): Number of areas the feature map is divided.
+            residual (bool): Whether to use residual connections with learnable gamma parameter.
+            mlp_ratio (float): Expansion ratio for MLP hidden dimension.
+            e (float): Channel expansion ratio for hidden channels.
+            g (int): Number of groups for grouped convolutions.
+            shortcut (bool): Whether to use shortcut connections in C3k blocks.
+        """
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        assert c_ % 32 == 0, "Dimension of ABlock be a multiple of 32."
+
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv((1 + n) * c_, c2, 1)
+
+        self.gamma = nn.Parameter(0.01 * torch.ones(c2), requires_grad=True) if a2 and residual else None
+        self.m = nn.ModuleList(
+            nn.Sequential(*(ABlock(c_, c_ // 32, mlp_ratio, area) for _ in range(2)))
+            if a2
+            else C3k(c_, c_, 2, shortcut, g)
+            for _ in range(n)
+        )
+
+    def forward(self, x):
+        """Forward pass through R-ELAN layer."""
+        y = [self.cv1(x)]
+        y.extend(m(y[-1]) for m in self.m)
+        y = self.cv2(torch.cat(y, 1))
+        if self.gamma is not None:
+            return x + self.gamma.view(-1, len(self.gamma), 1, 1) * y
+        return y

ultralytics/nn/tasks.py

@@ -22,6 +22,7 @@ from ultralytics.nn.modules import (
     SPP,
     SPPELAN,
     SPPF,
+    A2C2f,
     AConv,
     ADown,
     Bottleneck,
@@ -637,8 +638,8 @@ class WorldModel(DetectionModel):
             (torch.Tensor): Model's output tensor.
         """
         txt_feats = (self.txt_feats if txt_feats is None else txt_feats).to(device=x.device, dtype=x.dtype)
-        if len(txt_feats) != len(x):
-            txt_feats = txt_feats.repeat(len(x), 1, 1)
+        if len(txt_feats) != len(x) or self.model[-1].export:
+            txt_feats = txt_feats.expand(x.shape[0], -1, -1)
         ori_txt_feats = txt_feats.clone()
         y, dt, embeddings = [], [], []  # outputs
         for m in self.model:  # except the head part
@@ -985,6 +986,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
             PSA,
             SCDown,
             C2fCIB,
+            A2C2f,
         }
     )
     repeat_modules = frozenset(  # modules with 'repeat' arguments
@@ -1003,6 +1005,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
             C2fPSA,
             C2fCIB,
             C2PSA,
+            A2C2f,
         }
     )
     for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]):  # from, number, module, args
@@ -1034,6 +1037,10 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
                 legacy = False
                 if scale in "mlx":
                     args[3] = True
+            if m is A2C2f:
+                legacy = False
+                if scale in "lx":  # for L/X sizes
+                    args.extend((True, 1.2))
         elif m is AIFI:
             args = [ch[f], *args]
         elif m in frozenset({HGStem, HGBlock}):

ultralytics/utils/callbacks/comet.py

@@ -177,7 +177,7 @@ def _format_ground_truth_annotations_for_detection(img_idx, image_path, batch, c
     return {"name": "ground_truth", "data": data}
 
 
-def _format_prediction_annotations_for_detection(image_path, metadata, class_label_map=None):
+def _format_prediction_annotations_for_detection(image_path, metadata, class_label_map=None, class_map=None):
     """Format YOLO predictions for object detection visualization."""
     stem = image_path.stem
     image_id = int(stem) if stem.isnumeric() else stem
@@ -187,26 +187,32 @@ def _format_prediction_annotations_for_detection(image_path, metadata, class_lab
         LOGGER.debug(f"COMET WARNING: Image: {image_path} has no bounding boxes predictions")
         return None
 
+    label_index_offset = 0
+    if class_map is not None:
+        # offset to align indices of class labels (starting from zero)
+        # with prediction's category ID indices (can start from one)
+        label_index_offset = sorted(class_map)[0]
+
     data = []
     for prediction in predictions:
         boxes = prediction["bbox"]
         score = _scale_confidence_score(prediction["score"])
         cls_label = prediction["category_id"]
         if class_label_map:
-            cls_label = str(class_label_map[cls_label])
+            cls_label = str(class_label_map[cls_label - label_index_offset])
 
         data.append({"boxes": [boxes], "label": cls_label, "score": score})
 
     return {"name": "prediction", "data": data}
 
 
-def _fetch_annotations(img_idx, image_path, batch, prediction_metadata_map, class_label_map):
+def _fetch_annotations(img_idx, image_path, batch, prediction_metadata_map, class_label_map, class_map):
     """Join the ground truth and prediction annotations if they exist."""
     ground_truth_annotations = _format_ground_truth_annotations_for_detection(
         img_idx, image_path, batch, class_label_map
     )
     prediction_annotations = _format_prediction_annotations_for_detection(
-        image_path, prediction_metadata_map, class_label_map
+        image_path, prediction_metadata_map, class_label_map, class_map
     )
 
     annotations = [
@@ -260,6 +266,7 @@ def _log_image_predictions(experiment, validator, curr_step):
     predictions_metadata_map = _create_prediction_metadata_map(jdict)
     dataloader = validator.dataloader
     class_label_map = validator.names
+    class_map = getattr(validator, "class_map", None)
 
     batch_logging_interval = _get_eval_batch_logging_interval()
     max_image_predictions = _get_max_image_predictions_to_log()
@@ -280,6 +287,7 @@ def _log_image_predictions(experiment, validator, curr_step):
                 batch,
                 predictions_metadata_map,
                 class_label_map,
+                class_map=class_map,
             )
             _log_images(
                 experiment,

ultralytics/utils/downloads.py

@@ -18,6 +18,7 @@ GITHUB_ASSETS_REPO = "ultralytics/assets"
 GITHUB_ASSETS_NAMES = (
     [f"yolov8{k}{suffix}.pt" for k in "nsmlx" for suffix in ("", "-cls", "-seg", "-pose", "-obb", "-oiv7")]
     + [f"yolo11{k}{suffix}.pt" for k in "nsmlx" for suffix in ("", "-cls", "-seg", "-pose", "-obb")]
+    + [f"yolo12{k}{suffix}.pt" for k in "nsmlx" for suffix in ("",)]  # detect models only currently
     + [f"yolov5{k}{resolution}u.pt" for k in "nsmlx" for resolution in ("", "6")]
     + [f"yolov3{k}u.pt" for k in ("", "-spp", "-tiny")]
     + [f"yolov8{k}-world.pt" for k in "smlx"]

ultralytics/utils/metrics.py

@@ -604,7 +604,7 @@ def ap_per_class(
             if j == 0:
                 prec_values.append(np.interp(x, mrec, mpre))  # precision at mAP@0.5
 
-    prec_values = np.array(prec_values)  # (nc, 1000)
+    prec_values = np.array(prec_values) if prec_values else np.zeros((1, 1000))  # (nc, 1000)
 
     # Compute F1 (harmonic mean of precision and recall)
     f1_curve = 2 * p_curve * r_curve / (p_curve + r_curve + eps)

ultralytics/utils/torch_utils.py

@@ -317,8 +317,7 @@ def model_info(model, detailed=False, verbose=True, imgsz=640):
             if len(m._parameters):
                 for pn, p in m.named_parameters():
                     LOGGER.info(
-                        f"{i:>5g}{mn + '.' + pn:>40}{mt:>20}{p.requires_grad!r:>10}{p.numel():>12g}"
-                        f"{str(list(p.shape)):>20}{p.mean():>10.3g}{p.std():>10.3g}{str(p.dtype).replace('torch.', ''):>15}"
+                        f"{i:>5g}{f'{mn}.{pn}':>40}{mt:>20}{p.requires_grad!r:>10}{p.numel():>12g}{str(list(p.shape)):>20}{p.mean():>10.3g}{p.std():>10.3g}{str(p.dtype).replace('torch.', ''):>15}"
                     )
             else:  # layers with no learnable params
                 LOGGER.info(f"{i:>5g}{mn:>40}{mt:>20}{False!r:>10}{0:>12g}{str([]):>20}{'-':>10}{'-':>10}{'-':>15}")

{ultralytics-8.3.77.dist-info → ultralytics-8.3.79.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ultralytics
-Version: 8.3.77
+Version: 8.3.79
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>

{ultralytics-8.3.77.dist-info → ultralytics-8.3.79.dist-info}/RECORD

@@ -7,7 +7,7 @@ tests/test_exports.py,sha256=T_z_NUS9URQXv83k5XNLHTuksJ8srtzbZnWuiiQWM98,9260
 tests/test_integrations.py,sha256=p3DMnnPMKsV0Qm82JVJUIY1UZ67xRgF9E8AaL76TEHE,6154
 tests/test_python.py,sha256=tW-EFJC2rjl_DvAa8khXGWYdypseQjrLjGHhe2p9r9A,23238
 tests/test_solutions.py,sha256=aY0G3vNzXGCENG9FD76MfUp7jgzeESPsUvbvQYBUvH0,4205
-ultralytics/__init__.py,sha256=HQtHuvQM5kuWiBsRP3s4mhhbcYU2HsTkCBcXce66zkY,709
+ultralytics/__init__.py,sha256=moo1vmbr78zE56S4YpmOEngnomz8U-tJpyjDtGNeJxA,709
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=qP44HnFP4QcC5FQz29A-EGTuwdtxXAzPvw_IvCVmiqA,39771
@@ -48,6 +48,11 @@ ultralytics/cfg/models/11/yolo11-obb.yaml,sha256=x8XDI2WvbBDre79eslYafBDvu6AmdGb
 ultralytics/cfg/models/11/yolo11-pose.yaml,sha256=RUe-8rIrrYWItv0GMo_VaO9JfrK2NJSXfbhv0NOq9dk,2128
 ultralytics/cfg/models/11/yolo11-seg.yaml,sha256=ozw5daUucWFCnJNVApK8TIijSe2qAlFmq_VoPyVu9Oo,2045
 ultralytics/cfg/models/11/yolo11.yaml,sha256=5XryDSNt5MYaIhTnGOJYnFV8xRiZPsGcsayYt0RCSJM,2012
+ultralytics/cfg/models/12/yolo12-cls.yaml,sha256=BLv578ZuU-QKx6GTNWX6lXdutzf_0rGhRrC3HrpxaNM,1405
+ultralytics/cfg/models/12/yolo12-obb.yaml,sha256=JMviFAOmDbW0aMNzZNqispP0wxWw3mtKn2iUwedf4WM,1975
+ultralytics/cfg/models/12/yolo12-pose.yaml,sha256=Mr9xjYclLQzxYhMqjIKQTdiTvtqZvEXBtclADFggaMA,2074
+ultralytics/cfg/models/12/yolo12-seg.yaml,sha256=RBFFz4b95Dupfg0fmqCkZ4i1Zzai_QyJrI6Y2oLsocM,1984
+ultralytics/cfg/models/12/yolo12.yaml,sha256=ZeA8LuymJXPNjZ5xkxkZHkcktDaKDzUBb2Kc3gCLC1w,1953
 ultralytics/cfg/models/rt-detr/rtdetr-l.yaml,sha256=_jGu4rotBnmjS29MkSvPx_4dNTWku68ie8-BIvf_p6Q,2041
 ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml,sha256=BGWp61olKkgD_CzikeVSglWfat3L9hDIK6KDkjwzlxc,1678
 ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml,sha256=hrRmoL2w-Rchd7obEcSYPeyDNG32QxXftbRH_4vVeZQ,1676
@@ -92,21 +97,21 @@ ultralytics/cfg/solutions/default.yaml,sha256=c-9thwI7y7VmIoIM6AW70Z0r825SToH2h7
 ultralytics/cfg/trackers/botsort.yaml,sha256=D9doE5GQUe6HrAFzr7OfQFIGPFk0M_vJ0B_n7VjxH6Q,1080
 ultralytics/cfg/trackers/bytetrack.yaml,sha256=6u-tiZlk16EqEwkNXaMrza6PAQmWj_ypgv26LGCtPDg,886
 ultralytics/data/__init__.py,sha256=nAXaL1puCc7z_NjzQNlJnhbVhT9Fla2u7Dsqo7q1dAc,644
-ultralytics/data/annotator.py,sha256=jbKHB5l5IYOG1YOgCxA6czU_ivb3NPAACrtPe6-bVn4,3145
-ultralytics/data/augment.py,sha256=sQDtIPD0P2pm_t-dI87hZt9KTB2PDN0JT_7AekHctRw,120726
+ultralytics/data/annotator.py,sha256=whx_3sdKGRsECYLKyJMNGQ-d9g-f8020O6kvl5M1c_I,3067
+ultralytics/data/augment.py,sha256=XFrIPNI7un1aLdL3ZU24mwKLRd1AvUSPgie7s3Pb6OE,121319
 ultralytics/data/base.py,sha256=NTNdn-Emgx3Z2vats8i8oEe-9yosPmHd53v1A0xz0EU,15196
 ultralytics/data/build.py,sha256=gOU5SNABBNxwo5012N--WhjEnLK2ewycXIryMpbHg6U,7685
-ultralytics/data/converter.py,sha256=89E44LBCpbn5hMF03Kdts6DaTP8Oei5iCra5enFCt5I,24467
+ultralytics/data/converter.py,sha256=M7LvBpdYiDA_YEuef3oCXhGPFTjtyJjSbSwqn-F6d7I,24473
 ultralytics/data/dataset.py,sha256=lxtH3JytNu6nsiPAIhe0uGuGGpkZ4ZRqvXM6eJw9rXU,23244
 ultralytics/data/loaders.py,sha256=JOwXbz-dxgG2bx0_cQHp-olz5FleoCX8EzrUvZ77vvg,28534
 ultralytics/data/split_dota.py,sha256=YI-i2MqdiBt06W67TJnBXQHJrqTnkJDJ3zzoL0UZVro,10733
 ultralytics/data/utils.py,sha256=5YMU5396oAFPwTy2y0MCU2WipF6Rt-7xNtmHKRCA4fI,33838
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=nrO0UdRMzhb_hp-IXAstBmMHJoax-P7Fqe7a8u2954A,77113
+ultralytics/engine/exporter.py,sha256=qeEV-w8cdYuVJP4RaKbq46xJmsYGUFJnkplfEUCIm_c,77013
 ultralytics/engine/model.py,sha256=s8HsSBvdRgSbnKGULr7YW-ZWJKJsQpOoHd9Aih_nMt0,53427
 ultralytics/engine/predictor.py,sha256=jiYDAjupOlRUpPvw9tu7or9PjXtLm-YCRiawANtWxj0,17881
 ultralytics/engine/results.py,sha256=hWlO2e58BPUJ5R4Jl4iirBPaZ8BypcNu_cNQ2NHpUqM,78111
-ultralytics/engine/trainer.py,sha256=hrqaO3cgf0VPVLHKv0tHk4W3gcasgqq_KF-DkgnIjus,37421
+ultralytics/engine/trainer.py,sha256=pV8sztWxFH5rMNYW0wXHlk-YrVZsEUYAKFvfcA22PnY,37600
 ultralytics/engine/tuner.py,sha256=EUlTs7KJQ2RVABm8pihr_14M_Z2kGSzJaWH-Y9TJYDw,11976
 ultralytics/engine/validator.py,sha256=r27X8HGeDEwq7V5sFjEQH_3EnP1CyG-HcOLpFABUisU,15034
 ultralytics/hub/__init__.py,sha256=1ifzSYV0PIT4ZWOm2V7HnpGyY3G3hCz0malw3AXHFlY,5660
@@ -126,9 +131,9 @@ ultralytics/models/nas/predict.py,sha256=nzVGTdUb0E_IjmWksX_T61q80hbrjEovihTzTJ1
 ultralytics/models/nas/val.py,sha256=CSqmcuAcuJ5SQ7mo364RdXLGeu2XATyRY8Z84VGGX5o,1497
 ultralytics/models/rtdetr/__init__.py,sha256=_jEHmOjI_QP_nT3XJXLgYHQ6bXG4EL8Gnvn1y_eev1g,225
 ultralytics/models/rtdetr/model.py,sha256=KFUlxMo2NTxVvK9D5x9p0WhXogK_QL5Wao8KxcZcT7s,2016
-ultralytics/models/rtdetr/predict.py,sha256=ymZS4ocUuec7zEOOnKFr2xaAr48NwljibO8DE_VrTwY,3596
+ultralytics/models/rtdetr/predict.py,sha256=zT4rc2M0drf1ge1FhWc6RG7tg6xgRdCroXlnl2tJJCI,3598
 ultralytics/models/rtdetr/train.py,sha256=TGawTiBD0SkNaCS8mWc3KbhfiviPuA7GWkvpZ8xVpGM,3875
-ultralytics/models/rtdetr/val.py,sha256=A2Um_J7GE6EHDOHCABpcy4ApyBKT_r9IquguCeROQ7I,5594
+ultralytics/models/rtdetr/val.py,sha256=cve1HdfLI-hGM2dkTCDT_cOFfDuzAe2ROkmlJOZC4qw,5595
 ultralytics/models/sam/__init__.py,sha256=qZwyxJf34UuE5Lu9qfblVXUAvK1fVd66Xyut_ZcTdyc,246
 ultralytics/models/sam/amg.py,sha256=MsTflp_oyTjQkfgYZCyn_HVpGOw4f-XH7vDSbM9mRRI,8736
 ultralytics/models/sam/build.py,sha256=Vhml3zBGDcRO-efauNdM0ZlKTV10ADAj_aT823lPJv8,12515
@@ -155,7 +160,7 @@ ultralytics/models/yolo/classify/val.py,sha256=VUYkqGtKnZPig1XE5Qrtqoqm-Y9dDgr5Y
 ultralytics/models/yolo/detect/__init__.py,sha256=GIRsLYR-kT4JJx7lh4ZZAFGBZj0aebokuU0A7JbjDVA,257
 ultralytics/models/yolo/detect/predict.py,sha256=_RrKS3h-tRR4uJyTOPSIp4HapxXC-c8Ao9yDeAM835I,2852
 ultralytics/models/yolo/detect/train.py,sha256=Y2SYjywenBLg8j-r4bC_sWqle1DJGQtDL5O6koeqm9U,6738
-ultralytics/models/yolo/detect/val.py,sha256=ZzJ2mEKoiUI8yfgE5nx1zUV-51_78z5s8REUbBr7wU8,15253
+ultralytics/models/yolo/detect/val.py,sha256=V06zB_CSKCdVu8r7e_0mi9h749qe32FdZI7VssZPoDk,15231
 ultralytics/models/yolo/obb/__init__.py,sha256=tQmpG8wVHsajWkZdmD6cjGohJ4ki64iSXQT8JY_dydo,221
 ultralytics/models/yolo/obb/predict.py,sha256=SUgLzsxg1O77KxIeCj9IlSiqB9SfIwcoRtNZViqPS2E,1880
 ultralytics/models/yolo/obb/train.py,sha256=7LJ04dYENfjdt1Jet0Cxh0nyIpmgIUtmz425ZEuZSn8,1550
@@ -172,11 +177,11 @@ ultralytics/models/yolo/world/__init__.py,sha256=nlh8I6t8hMGz_vZg8QSlsUW1R-2eKvn
 ultralytics/models/yolo/world/train.py,sha256=6PVmQ0G-22OOPPwP_rqSobe2LM6e2b_lC7lJCdW3UIk,3714
 ultralytics/models/yolo/world/train_world.py,sha256=sCtg4Hnq9Y7amYjlQsdvTHXH8cKSooipvcXu_1Iyb2k,4885
 ultralytics/nn/__init__.py,sha256=rjociYD9lo_K-d-1s6TbdWklPLjTcEHk7OIlRDJstIE,615
-ultralytics/nn/autobackend.py,sha256=Sixewlem0qeGCD18Zihli1H25j1q71957L33kpVfrVE,37365
-ultralytics/nn/tasks.py,sha256=VxtdV1OVpIatZBHmHgIRHuJ9FY4sLAN96VSKeeOhNg8,48796
-ultralytics/nn/modules/__init__.py,sha256=02dPoAMtpPNQdHXHmvJeWZvJ_WG6eqwH8atLdFWgcuY,2713
+ultralytics/nn/autobackend.py,sha256=uVLr4GymWtz4D86QXzmqs7LwoLjv3VycFLfdKq9rG1U,37377
+ultralytics/nn/tasks.py,sha256=rKyTShwk1RtWBnbHObcSamxXoCUiwzl0K5QFYaw56Hw,49030
+ultralytics/nn/modules/__init__.py,sha256=pVV5SSu6ktOusdVFr1kHK_WOkVLjCLO2W5XaLH-NF8w,2737
 ultralytics/nn/modules/activation.py,sha256=oRkhMdqlNpIxQb35pTSUeHV-h0VyLl96GOqvIZ4OvT8,923
-ultralytics/nn/modules/block.py,sha256=vQqfKIXPmEnxupdzcLDGC5FkjCNIqURfqt4CEEseuXE,43940
+ultralytics/nn/modules/block.py,sha256=z0F0YD07C31VyMdYCeT5KoTgTpazIYW34xH7xgy02J4,52166
 ultralytics/nn/modules/conv.py,sha256=Wx_tZ56M7iMiNqz3v03oi86C2fatdmdBBDpkrUyzEIU,13132
 ultralytics/nn/modules/head.py,sha256=RYT31wplr64yDSHLpEZy3fyqg9W8HWlXWKrltwpqGiQ,27962
 ultralytics/nn/modules/transformer.py,sha256=fdc4xam82Dk8etahkhlc5RHW6dfY00klKj2od4QpdQo,18097
@@ -209,23 +214,23 @@ ultralytics/utils/autobatch.py,sha256=zc81HlAMArPASEbExty0E_zpITF8PVwin7w-xBFFZ5
 ultralytics/utils/benchmarks.py,sha256=enf8emMQ7OcZa6RokvwrNm4ZfW-XS7SBKp57staqGRM,26751
 ultralytics/utils/checks.py,sha256=Hz7yLxQHqzYJkL3HmGy6nhHLG2eYjwH5B0BK5GXV9a4,31011
 ultralytics/utils/dist.py,sha256=fuiJQEnyyL-SighlI3hUlZPaaSreUl4Q39snF6OhQtI,2386
-ultralytics/utils/downloads.py,sha256=aUESyJOE2d7mJwbGECHWLR3RF8HVQPSwNH0cfmLGgdI,21999
+ultralytics/utils/downloads.py,sha256=5B1uwRr6Urb5ShZAAni5_tq9a-3o0fSAH3xNCULktFY,22100
 ultralytics/utils/errors.py,sha256=sXKDEd8ws3L-yIfG_-P_h86axbm37sJNha7kFBJbQMQ,844
 ultralytics/utils/files.py,sha256=c85NRofjGPMcpkV-yUo1Cwk8ZVquBGCEKlzbSVtXkQA,8252
 ultralytics/utils/instance.py,sha256=z1oyyvz7wnCSUW_bvi0TbgAL0VxJtAWWXV9KWCoyJ_k,16887
 ultralytics/utils/loss.py,sha256=paRY8K7R4pcUGJfApVzZx-m_iFzzMbHm5GgiaixfDuU,34179
-ultralytics/utils/metrics.py,sha256=6RBMTBbTYa-5nRwTPlbPBX8w9xhpqryZ9tjXsvlRmmM,54184
+ultralytics/utils/metrics.py,sha256=M15LVYzTGgmahkALKwKU3iYDoJIZ3M4824FLqsJ9qeU,54224
 ultralytics/utils/ops.py,sha256=izQr5GvgzmaD-GXaqxIjLE525JnvgLetOtuq_EOaxM8,34584
 ultralytics/utils/patches.py,sha256=ARR89dP4YKq7Dd3g2eU-ukbnc2lo3BELukL_1c_d854,3298
 ultralytics/utils/plotting.py,sha256=hKji4TyxAmCXdSL264VX6dsC2AZYiL9StShI02dcAOM,62990
 ultralytics/utils/tal.py,sha256=DO-c006HEI62pcrNRpmt4lpqJPC5yu3veRDOvUuExno,18498
-ultralytics/utils/torch_utils.py,sha256=wmV-mlv-vQzAwk66TILC_nEFhlGx5udrGlQqTenqnBw,34068
+ultralytics/utils/torch_utils.py,sha256=h1aWTJ71NX5Q_L5ZAj-4Yljht5S_6YEhE2XUm2Apt2M,34039
 ultralytics/utils/triton.py,sha256=2L1_rZ8xCJEjexRVj75g9YU-u4tQln_DJ5N1Yr_0bSs,4071
 ultralytics/utils/tuner.py,sha256=gySDBzTlq_klTOq6CGEyUN58HXzPCulObaMBHacXzHo,6294
 ultralytics/utils/callbacks/__init__.py,sha256=hzL63Rce6VkZhP4Lcim9LKjadixaQG86nKqPhk7IkS0,242
 ultralytics/utils/callbacks/base.py,sha256=nbeSPjPCOb0M6FsFQ5-uFxXVzUYwmFyE4wFoA66Jpug,5803
 ultralytics/utils/callbacks/clearml.py,sha256=JH70T1OLPd9GSvC6HnaKkZHTr8fyE9RRcz3ukL62QPw,5961
-ultralytics/utils/callbacks/comet.py,sha256=RfijX3oKLdI3zXyleATLmkGfaV--3sBU-V-zyX8-TWU,15607
+ultralytics/utils/callbacks/comet.py,sha256=2fO79Lvl3DqJmM6zX5COU1Xt3IN_GTkzrDQWr9a80Ag,16005
 ultralytics/utils/callbacks/dvc.py,sha256=4ln4wqU3ZZTK5JfvUmbKfQuIdO6QohDSnFVV4v5Pl8E,5073
 ultralytics/utils/callbacks/hub.py,sha256=bqU83kBnNZ0U9qjm0I9xvM4DWA0VMxSLxQDgjuTZbKM,3977
 ultralytics/utils/callbacks/mlflow.py,sha256=3y4xOPLZe1bES0ETWGJYywulTEUGv8I849e2TNms8yI,5420
@@ -233,9 +238,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=waZ_bRu0-qBKujTLuqonC2gx2DkgBuVnfq
 ultralytics/utils/callbacks/raytune.py,sha256=A_NVWjyPNf2m6iB-mbW7SMpyqM9QBvpbPa-MCMFMtdk,727
 ultralytics/utils/callbacks/tensorboard.py,sha256=JHOEVlNQ5dYJPd4Z-EvqbXowuK5uA0p8wPgyyaIUQs0,4194
 ultralytics/utils/callbacks/wb.py,sha256=ayhT2y62AcSOacnawshATU0rWrlSFQ77mrGgBdRl3W4,7086
-ultralytics-8.3.77.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.77.dist-info/METADATA,sha256=QxzCR22FPcNMdABaAuLci--YfzTs5Y_7Nz-2vywjMfE,35158
-ultralytics-8.3.77.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ultralytics-8.3.77.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.77.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.77.dist-info/RECORD,,
+ultralytics-8.3.79.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.79.dist-info/METADATA,sha256=Qg8FyAGAg92474miDCJhNUdGM-siQ8ypdixaKpzYyko,35158
+ultralytics-8.3.79.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ultralytics-8.3.79.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.79.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.79.dist-info/RECORD,,